An Improved Machine Learning Based Automatic Lung Nodule Identifier

Lung cancer is one of the most critical diseases due to its significant death rate compared to all other types of cancer. The early diagnosis of lung cancer that improves the patient's chance of surviving is mostly done in two phases: screening through CT scan imaging modality and, more importantly, the medical expert's reading of the scan, which is a time-consuming task and is vulnerable to errors. Even so, to increase the effectiveness of the analysis procedure within a shorter period of time, the research community has developed a CADx system to be used as a second opinion by radiologists. In this study, a CNN-based computer-aided diagnosis system proposed to automatically classify pulmonary nodules into benign or malignant. The system can be used by clinicians as an assistant during the diagnosing process. The network has been trained, validated, and tested using 20,000 samples from a DSB dataset that was combined with 2,490 samples from the lungx dataset. In order to build a well-trained model, several pre-processing steps are applied to the entire dataset, for instance segmentation, normalization, and zero centring. Finally, the proposed system obtained results with 0.987% accuracy, 0.986 sensitivity, and 0.989 specificity. Citation: Dr. T. Velumani. "An Improved Machine Learning Based Automatic Lung Nodule Identifier." Global Research and Development Journal For Engineering 6.11 (2021): 1 - 8.